summaryrefslogtreecommitdiff
path: root/myisam/ft_parser.c
blob: 2fad2363ae205b561aa88ee6884bca395775cfea (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
/* Copyright (C) 2000 MySQL AB & MySQL Finland AB & TCX DataKonsult AB

   This program is free software; you can redistribute it and/or modify
   it under the terms of the GNU General Public License as published by
   the Free Software Foundation; either version 2 of the License, or
   (at your option) any later version.

   This program is distributed in the hope that it will be useful,
   but WITHOUT ANY WARRANTY; without even the implied warranty of
   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
   GNU General Public License for more details.

   You should have received a copy of the GNU General Public License
   along with this program; if not, write to the Free Software
   Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA */

/* Written by Sergei A. Golubchik, who has a shared copyright to this code */

#include "ftdefs.h"

typedef struct st_ft_docstat {
  FT_WORD *list;
  uint uniq;
  double sum;
} FT_DOCSTAT;

static int FT_WORD_cmp(CHARSET_INFO* cs, FT_WORD *w1, FT_WORD *w2)
{
  return mi_compare_text(cs, (uchar*) w1->pos, w1->len,
                         (uchar*) w2->pos, w2->len, 0, 0);
}

static int walk_and_copy(FT_WORD *word,uint32 count,FT_DOCSTAT *docstat)
{
    word->weight=LWS_IN_USE;
    docstat->sum+=word->weight;
    memcpy_fixed((docstat->list)++,word,sizeof(FT_WORD));
    return 0;
}

/* transforms tree of words into the array, applying normalization */

FT_WORD * ft_linearize(TREE *wtree)
{
  FT_WORD *wlist,*p;
  FT_DOCSTAT docstat;
  DBUG_ENTER("ft_linearize");

  if ((wlist=(FT_WORD *) my_malloc(sizeof(FT_WORD)*
				   (1+wtree->elements_in_tree),MYF(0))))
  {
    docstat.list=wlist;
    docstat.uniq=wtree->elements_in_tree;
    docstat.sum=0;
    tree_walk(wtree,(tree_walk_action)&walk_and_copy,&docstat,left_root_right);
  }
  delete_tree(wtree);
  if (!wlist)
    DBUG_RETURN(NULL);

  docstat.list->pos=NULL;

  for (p=wlist;p->pos;p++)
  {
    p->weight=PRENORM_IN_USE;
  }

  for (p=wlist;p->pos;p++)
  {
    p->weight/=NORM_IN_USE;
  }

  DBUG_RETURN(wlist);
}

my_bool ft_boolean_check_syntax_string(const byte *str)
{
  uint i, j;

  if (!str ||
      (strlen(str)+1 != sizeof(ft_boolean_syntax)) ||
      (str[0] != ' ' && str[1] != ' '))
    return 1;
  for (i=0; i<sizeof(ft_boolean_syntax); i++)
  {
    /* limiting to 7-bit ascii only */
    if ((unsigned char)(str[i]) > 127 || my_isalnum(default_charset_info, str[i]))
      return 1;
    for (j=0; j<i; j++)
      if (str[i] == str[j] && (i != 11 || j != 10))
        return 1;
  }
  return 0;
}

/*
  RETURN VALUE
  0 - eof
  1 - word found
  2 - left bracket
  3 - right bracket
  4 - stopword found
*/
byte ft_get_word(CHARSET_INFO *cs, byte **start, byte *end,
                 FT_WORD *word, FTB_PARAM *param)
{
  byte *doc=*start;
  uint mwc, length, mbl;

  param->yesno=(FTB_YES==' ') ? 1 : (param->quot != 0);
  param->plusminus=param->pmsign=0;

  while (doc<end)
  {
    for (;doc<end;doc++)
    {
      if (true_word_char(cs,*doc)) break;
      if (*doc == FTB_RQUOT && param->quot)
      {
        param->quot=doc;
        *start=doc+1;
        return 3; /* FTB_RBR */
      }
      if (!param->quot)
      {
        if (*doc == FTB_LBR || *doc == FTB_RBR || *doc == FTB_LQUOT)
        {
          /* param->prev=' '; */
          *start=doc+1;
          if (*doc == FTB_LQUOT) param->quot=*start;
          return (*doc == FTB_RBR)+2;
        }
        if (param->prev == ' ')
        {
          if (*doc == FTB_YES ) { param->yesno=+1;    continue; } else
          if (*doc == FTB_EGAL) { param->yesno= 0;    continue; } else
          if (*doc == FTB_NO  ) { param->yesno=-1;    continue; } else
          if (*doc == FTB_INC ) { param->plusminus++; continue; } else
          if (*doc == FTB_DEC ) { param->plusminus--; continue; } else
          if (*doc == FTB_NEG ) { param->pmsign=!param->pmsign; continue; }
        }
      }
      param->prev=*doc;
      param->yesno=(FTB_YES==' ') ? 1 : (param->quot != 0);
      param->plusminus=param->pmsign=0;
    }

    mwc=length=0;
    for (word->pos=doc; doc<end; length++, mbl=my_mbcharlen(cs, *(uchar *)doc), doc+=(mbl ? mbl : 1))
      if (true_word_char(cs,*doc))
        mwc=0;
      else if (!misc_word_char(*doc) || mwc++)
        break;

    param->prev='A'; /* be sure *prev is true_word_char */
    word->len= (uint)(doc-word->pos) - mwc;
    if ((param->trunc=(doc<end && *doc == FTB_TRUNC)))
      doc++;

    if (((length >= ft_min_word_len && !is_stopword(word->pos, word->len))
         || param->trunc) && length < ft_max_word_len)
    {
      *start=doc;
      return 1;
    }
    else if (length) /* make sure length > 0 (if start contains spaces only) */
    {
      *start= doc;
      return 4;
    }
  }
  if (param->quot)
  {
    param->quot=*start=doc;
    return 3; /* FTB_RBR */
  }
  return 0;
}

byte ft_simple_get_word(CHARSET_INFO *cs, byte **start, const byte *end,
                        FT_WORD *word, my_bool skip_stopwords)
{
  byte *doc= *start;
  uint mwc, length, mbl;
  DBUG_ENTER("ft_simple_get_word");

  do
  {
    for (;; doc++)
    {
      if (doc >= end) DBUG_RETURN(0);
      if (true_word_char(cs, *doc)) break;
    }

    mwc= length= 0;
    for (word->pos=doc; doc<end; length++, mbl=my_mbcharlen(cs, *(uchar *)doc), doc+=(mbl ? mbl : 1))
      if (true_word_char(cs,*doc))
        mwc= 0;
      else if (!misc_word_char(*doc) || mwc++)
        break;

    word->len= (uint)(doc-word->pos) - mwc;

    if (skip_stopwords == FALSE ||
        (length >= ft_min_word_len && length < ft_max_word_len &&
         !is_stopword(word->pos, word->len)))
    {
      *start= doc;
      DBUG_RETURN(1);
    }
  } while (doc < end);
  DBUG_RETURN(0);
}

void ft_parse_init(TREE *wtree, CHARSET_INFO *cs)
{
  DBUG_ENTER("ft_parse_init");
  if (!is_tree_inited(wtree))
    init_tree(wtree,0,0,sizeof(FT_WORD),(qsort_cmp2)&FT_WORD_cmp,0,NULL, cs);
  DBUG_VOID_RETURN;
}

int ft_parse(TREE *wtree, byte *doc, int doclen, my_bool with_alloc)
{
  byte   *end=doc+doclen;
  FT_WORD w;
  DBUG_ENTER("ft_parse");

  while (ft_simple_get_word(wtree->custom_arg, &doc, end, &w, TRUE))
  {
    if (with_alloc)
    {
      byte *ptr;
      /* allocating the data in the tree - to avoid mallocs and frees */
      DBUG_ASSERT(wtree->with_delete==0);
      ptr=(byte *)alloc_root(& wtree->mem_root,w.len);
      memcpy(ptr, w.pos, w.len);
      w.pos=ptr;
    }
    if (!tree_insert(wtree, &w, 0, wtree->custom_arg))
      goto err;
  }
  DBUG_RETURN(0);

err:
  delete_tree(wtree);
  DBUG_RETURN(1);
}